© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59262
    Prev
    Next
    INDEX
    Explanations

    Butterfield or field

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ם
    0.95
    ی
    0.95
    ς
    0.88
    🙌
    0.85
    Я
    0.85
    波
    0.85
    时间
    0.84
    어
    0.84
    Y
    0.83
    ⁸
    0.83
    POSITIVE LOGITS
    la
    1.38
    l
    1.34
    ek
    1.30
    i
    1.23
    ia
    1.20
    r
    1.20
    p
    1.17
    d
    1.16
    at
    1.14
    om
    1.14
    Activations Density 0.001%

    No Known Activations